Comparison of manual and machine learning image processing approaches to determine fungiform papillae on the tongue.

Human taste perception is associated with the papillae on the tongue as they contain a large proportion of chemoreceptors for basic tastes and other chemosensation. Especially the density of fungiform papillae (FP) is considered as an index for responsiveness to oral chemosensory stimuli. The standard procedure for FP counting involves visual identification and manual counting of specific parts of the tongue by trained operators. This is a tedious task and automated image analysis methods are desirable. In this paper a machine learning image processing method based on a convolutional neural network is presented. This automated method was compared with three standard manual FP counting procedures using tongue pictures from 132 subjects. Automated FP counts, within the selected areas and the whole tongue, significantly correlated with the manual counting methods (all ρs ≥ 0.76). When comparing the images for gender and PROP status, the density of FP predicted from automated analysis was in good agreement with data from the manual counting methods, especially in the case of gender. Moreover, the present results reinforce the idea that caution should be applied in considering the relationship between FP density and PROP responsiveness since this relationship can be an oversimplification of the complexity of phenomena arising at the central and peripherical levels. Indeed, no significant correlations were found between FP and PROP bitterness ratings using the automated method for selected areas or the whole tongue. Besides providing estimates of the number of FP, the machine learning approach used a tongue coordinate system that normalizes the size and shape of an individual tongue and generated a heat map of the FP position and normalized area they cover. The present study demonstrated that the machine learning approach could provide similar estimates of FP on the tongue as compared to manual counting methods and provide estimates of more difficult-to-measure parameters, such as the papillae's areas and shape.

Inflammatory stimuli acutely modulate peripheral taste function.

Inflammation-mediated changes in taste perception can affect health outcomes in patients, but little is known about the underlying mechanisms. In the present work, we hypothesized that proinflammatory cytokines directly modulate Na(+) transport in taste buds. To test this, we measured acute changes in Na(+) flux in polarized fungiform taste buds loaded with a Na(+) indicator dye. IL-1ß elicited an amiloride-sensitive increase in Na(+) transport in taste buds. In contrast, TNF-α dramatically and reversibly decreased Na(+) flux in polarized taste buds via amiloride-sensitive and amiloride-insensitive Na(+) transport systems. The speed and partial amiloride sensitivity of these changes in Na(+) flux indicate that IL-1ß and TNF-α modulate epithelial Na(+) channel (ENaC) function. A portion of the TNF-mediated decrease in Na(+) flux is also blocked by the TRPV1 antagonist capsazepine, although TNF-α further reduced Na(+) transport independently of both amiloride and capsazepine. We also assessed taste function in vivo in a model of infection and inflammation that elevates these and additional cytokines. In rats administered systemic lipopolysaccharide (LPS), CT responses to Na(+) were significantly elevated between 1 and 2 h after LPS treatment. Low, normally preferred concentrations of NaCl and sodium acetate elicited high response magnitudes. Consistent with this outcome, codelivery of IL-1ß and TNF-α enhanced Na(+) flux in polarized taste buds. These results demonstrate that inflammation elicits swift changes in Na(+) taste function, which may limit salt consumption during illness.

Clinical applications and mechanism of intravenous taste tests.

It is well known that there are two ways to measure human blood circulation time: the arm-to-lung and the arm-to-tongue method. The decholin (20% dehydrocholic acid) test is usually used to measure the arm-to-tongue circulation time. In this study, this procedure was used to examine taste function. Findings on the clinical application of this intravenous taste test using decholin and a study on the mechanism of venous taste perception are reported here. The following method was used: Five ml of 20% decholin were injected into the right cubital vein over a 10-sec period and the latent time, the duration, the quality of the taste sensation and the region of the tongue where the taste appeared were noted. The results were as follows: 1) In dysgeusic subjects, the latent period was longer, and the duration of the taste sensation was shorter than in normal subjects (p is less than 0.01, p is less than 0.05). 2) Some of the dysgeusic subjects perceived the taste as other than bitter; their prognosis of taste dysfunction tended to be worse than that of other subjects. 3) Some of the dysgeusic subjects perceived the taste in regions of the tongue other than the bilateral edges or over the entire tongue; their prognosis of taste dysfunction tended to be worse than that of other subjects. 3) Some of the dysgeusic subjects perceived the taste in regions of the tongue other than bilateral edges or over the entire tongue; their prognosis tended to be worse than that of other subjects. In addition, photofluorograms of the tongue were taken to clarify the mechanism of intravenous taste; the time needed for fluorescence to appear in the fungiform papillae and their diffusion form in the papillae were observed and investigated.